Sparse-by-Design Cross-Modality Prediction: L0-Gated Representations for Reliable and Efficient Learning

ArXi:2603.26801v1 Announce Type: cross Predictive systems increasingly span heterogeneous modalities such as graphs, language, and tabular records, but sparsity and efficiency remain modality-specific (graph edge or neighborhood sparsification, Transformer head or layer pruning, and separate tabular feature-selection pipelines). This fragmentation makes results hard to compare, complicates deployment, and weakens reliability analysis across end-to-end KDD pipelines.